TR2023-001

Cross-Domain Video Anomaly Detection without Target Domain Adaptation


    •  Aich, A., Peng, K.-C., Roy-Chowdhury, A.K., "Cross-Domain Video Anomaly Detection without Target Domain Adaptation", IEEE Winter Conference on Applications of Computer Vision (WACV), January 2023.
      BibTeX TR2023-001 PDF Video Presentation
      • @inproceedings{Aich2023jan,
      • author = {Aich, Abhishek and Peng, Kuan-Chuan and Roy-Chowdhury, Amit K.},
      • title = {Cross-Domain Video Anomaly Detection without Target Domain Adaptation},
      • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
      • year = 2023,
      • month = jan,
      • url = {https://www.merl.com/publications/TR2023-001}
      • }
  • MERL Contact:
  • Research Areas:

    Computer Vision, Machine Learning

Abstract:

Most cross-domain unsupervised Video Anomaly Detection (VAD) works assume that at least few task-relevant target do- main training data are available for adaptation from the source to the target domain. However, this requires laborious model- tuning by the end-user who may prefer to have a system that works “out-of-the-box.” To address such practical scenarios, we identify a novel target domain (inference-time) VAD task where no target domain training data are available. To this end, we propose a new ‘Zero-shot Cross-domain Video Anomaly Detection (zxVAD)’ framework that includes a future-frame prediction generative model setup. Different from prior future- frame prediction models, our model uses a novel Normalcy Classifier module to learn the features of normal event videos by learning how such features are different “relatively” to features in pseudo-abnormal examples. A novel Untrained Convolu- tional Neural Network based Anomaly Synthesis module crafts these pseudo-abnormal examples by adding foreign objects in normal video frames with no extra training cost. With our novel relative normalcy feature learning strategy, zxVAD general- izes and learns to distinguish between normal and abnormal frames in a new target domain without adaptation during inference. Through evaluations on common datasets, we show that zxVAD outperformsthestate-of-the-art(SOTA),regardless of whether task-relevant (i.e., VAD) source training data are avail- able or not. Lastly, zxVAD also beats the SOTA methods in inference-time efficiency metrics including the model size, total parameters, GPU energy consumption, and GMACs.

 

  • Related Videos

  • Related Publication

  •  Aich, A., Peng, K.-C., Roy-Chowdhury, A.K., "Cross-Domain Video Anomaly Detection without Target Domain Adaptation", arXiv, December 2022.
    BibTeX arXiv
    • @article{Aich2022dec,
    • author = {Aich, Abhishek and Peng, Kuan-Chuan and Roy-Chowdhury, Amit K.},
    • title = {Cross-Domain Video Anomaly Detection without Target Domain Adaptation},
    • journal = {arXiv},
    • year = 2022,
    • month = dec,
    • url = {https://arxiv.org/abs/2212.07010}
    • }